File size: 2,708 Bytes
3cbb9cb 0d6acd9 d1d0c35 0d6acd9 3cbb9cb d1d0c35 3cbb9cb d1d0c35 fff9f28 e49982e 0d6acd9 3cbb9cb d1d0c35 3cbb9cb d1d0c35 3cbb9cb 0d6acd9 3cbb9cb 0d6acd9 3cbb9cb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2292920607623961,
"eval_steps": 10,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004585841215247922,
"eval_loss": NaN,
"eval_runtime": 52.288,
"eval_samples_per_second": 28.114,
"eval_steps_per_second": 3.519,
"step": 1
},
{
"epoch": 0.04585841215247922,
"grad_norm": NaN,
"learning_rate": 9.330127018922194e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.04585841215247922,
"eval_loss": NaN,
"eval_runtime": 51.2152,
"eval_samples_per_second": 28.702,
"eval_steps_per_second": 3.593,
"step": 10
},
{
"epoch": 0.09171682430495844,
"grad_norm": NaN,
"learning_rate": 6.91341716182545e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.09171682430495844,
"eval_loss": NaN,
"eval_runtime": 51.0501,
"eval_samples_per_second": 28.795,
"eval_steps_per_second": 3.604,
"step": 20
},
{
"epoch": 0.13757523645743766,
"grad_norm": NaN,
"learning_rate": 3.705904774487396e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.13757523645743766,
"eval_loss": NaN,
"eval_runtime": 51.1454,
"eval_samples_per_second": 28.742,
"eval_steps_per_second": 3.598,
"step": 30
},
{
"epoch": 0.18343364860991687,
"grad_norm": NaN,
"learning_rate": 1.0332332985438248e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.18343364860991687,
"eval_loss": NaN,
"eval_runtime": 51.1757,
"eval_samples_per_second": 28.725,
"eval_steps_per_second": 3.595,
"step": 40
},
{
"epoch": 0.2292920607623961,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.2292920607623961,
"eval_loss": NaN,
"eval_runtime": 51.3569,
"eval_samples_per_second": 28.623,
"eval_steps_per_second": 3.583,
"step": 50
}
],
"logging_steps": 10,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 13,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 7.36663625049047e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|